Custom-Trained Deep Learning-Based Auto-Segmentation for Male Pelvic Iterative CBCT on C-Arm Linear Accelerators.

PURPOSE: The purpose of this investigation was to evaluate the clinical applicability of a commercial artificial intelligence-driven deep learning auto-segmentation (DLAS) tool on enhanced iterative cone beam computed tomography (iCBCT) acquisitions for intact prostate and prostate bed treatments. METHODS AND MATERIALS: DLAS models were trained using 116 iCBCT data sets with manually delineated organs at risk (bladder, femoral heads, and rectum) and target volumes (intact prostate and prostate bed) adhering to institution-specific contouring guidelines. An additional 25 intact prostate and prostate bed iCBCT data sets were used for model testing. Segmentation accuracy relative to a reference structure set was quantified using various geometric comparison metrics and qualitatively evaluated by trained physicists and physicians. These results were compared with those obtained for an additional DLAS-based model trained on planning computed tomography (pCT) data sets and for a deformable image registration (DIR)-based automatic contour propagation method. RESULTS: In most instances, statistically significant differences in the Dice similarity coefficient (DSC), 95% directed Hausdorff distance, and mean surface distance metrics were observed between the models, as the iCBCT-trained DLAS model outperformed the pCT-trained DLAS model and DIR-based method for all organs at risk and the intact prostate target volume. Mean DSC values for the proposed method were ≥0.90 for these volumes of interest. The iCBCT-trained DLAS model demonstrated a relatively suboptimal performance for the prostate bed segmentation, as the mean DSC value was <0.75 for this target contour. Overall, 90% of bladder, 93% of femoral head, 67% of rectum, and 92% of intact prostate contours generated by the proposed method were deemed clinically acceptable based on qualitative scoring, and approximately 63% of prostate bed contours required moderate or major manual editing to adhere to institutional contouring guidelines. CONCLUSIONS: The proposed method presents the potential for improved segmentation accuracy and efficiency compared with the DIR-based automatic contour propagation method as commonly applied in CBCT-based dose evaluation and calculation studies.

Clinical Practice Evolvement for Post-Operative Prostate Cancer Radiotherapy-Part 1: Consistent Organs at Risk Management with Advanced Image Guidance.

Purpose: Post-operative prostate cancer patients are treated with full bladder instruction and the use of an endorectal balloon (ERB). We reassessed the efficacy of this practice based on daily image guidance and dose delivery using high-quality iterative reconstructed cone-beam CT (iCBCT). Methods: Fractional dose delivery was calculated on daily iCBCT for 314 fractions from 14 post-operative prostate patients (8 with and 6 without ERB) treated with volumetric modulated radiotherapy (VMAT). All patients were positioned using novel iCBCT during image guidance. The bladder, rectal wall, femoral heads, and prostate bed clinical tumor volume (CTV) were contoured and verified on daily iCBCT. The dose-volume parameters of the contoured organs at risk (OAR) and CTV coverage were assessed for the clinical impact of daily bladder volume variations and the use of ERB. Minimum bladder volume was studied, and a straightforward bladder instruction was explored for easy clinical adoption. Results: A "minimum bladder" contour, the overlap between the original bladder contour and a 15 mm anterior and superior expansion from prostate bed PTV, was confirmed to be effective in identifying cases that might fail a bladder constraint of V65% <60%. The average difference between the maximum and minimum bladder volumes for each patient was 277.1 mL. The daily bladder volumes varied from 62.4 to 590.7 mL and ranged from 29 to 286% of the corresponding planning bladder volume. The bladder constraint of V65% <60% was met in almost all fractions (98%). CTVs (D90%, D95%, and D98%) remained well-covered regardless of the absolute bladder volume daily variation or the presence of the endorectal balloon. Patients with an endorectal balloon showed smaller variation but a higher average maximum rectal wall dose (D0.03mL: 104.3% of the prescription) compared to patients without (103.3%). Conclusions: A "minimum bladder" contour was determined that can be easily generated and followed to ensure sufficient bladder sparing. Further analysis and validation are needed to confirm the utility of the minimal bladder contour. Accurate dose delivery can be achieved for prostate bed target coverage and OAR sparing with or without the use of ERB.

Improvements in treatment planning calculations motivated by tightening IMRT QA tolerances.

Implementing tighter intensity modulated radiation therapy (IMRT) quality assurance (QA) tolerances initially resulted in high numbers of marginal or failing QA results and motivated a number of improvements to our calculational processes. This work details those improvements and their effect on results. One hundred eighty IMRT plans analyzed previously were collected and new gamma criteria were applied and compared to the original results. The results were used to obtain an estimate for the number of plans that would require additional dose volume histogram (DVH)-based analysis and therefore predicted workload increase. For 2 months and 133 plans, the established criteria were continued while the new criteria were applied and tracked in parallel. Because the number of marginal or failing plans far exceeded the predicted levels, a number of calculational elements were investigated: IMRT modeling parameters, calculation grid size, and couch top modeling. After improvements to these elements, the new criteria were clinically implemented and the frequency of passing, questionable, and failing plans measured for the subsequent 15 months and 674 plans. The retrospective analysis of selected IMRT QA results demonstrated that 75% of plans should pass, while 19% of IMRT QA plans would need DVH-based analysis and an additional 6% would fail. However, after applying the tighter criteria for 2 months, the distribution of plans was significantly different from prediction with questionable or failing plans reaching 47%. After investigating and improving several elements of the IMRT calculation processes, the frequency of questionable plans was reduced to 11% and that of failing plans to less than 1%. Tighter IMRT QA tolerances revealed the need to improve several elements of our plan calculations. As a consequence, the accuracy of our plans have improved, and the frequency of finding marginal or failing IMRT QA results, remains within our practical ability to respond.

Technical Note: An efficient daily QA procedure for proton pencil beam scanning.

PURPOSE: The aim of this work was to develop an efficient daily quality assurance (QA) program with strict tolerance levels for pencil beam scanning (PBS) proton radiotherapy featuring simultaneous dosimetric testing on a single, nonuniform field. METHODS: A nonuniform field measuring beam output, proton range, and spot position was designed for delivery onto a Sun Nuclear Daily-QA 3 device. A custom acrylic block permitted simultaneous measurement of low- and high-energy proton ranges in addition to beam output. Sensitivities to output, range, and spot position were evaluated to quantitate the device's response. Reproducibility tests were used to identify and control sources of measurement error as well as to assess the QA procedure's robustness. This procedure was implemented in each of our four treatment rooms independently; 4-6 months of daily QA measurements were collected. RESULTS: The 1% output, 0.5 mm range, and 1.5 mm spot position tolerances derived from preliminary tests were tighter overall than tolerances found in the literature and equivalent to the limits used for proton system commissioning. The simplicity and automation of the procedure reduced the time required for daily QA to 10 min per treatment room, and competition for beam between multiple treatment rooms was minimized. CONCLUSIONS: An efficient daily PBS QA procedure can be performed using a single, nonuniform field on a nondedicated QA device. A thorough quantitation of the device's response and careful control of measurement uncertainties allowed daily tolerances to match commissioning standards.

Intensity-modulated radiotherapy-based stereotactic body radiotherapy for medically inoperable early-stage lung cancer: excellent local control.

PURPOSE: To validate the use of stereotactic body radiotherapy (SBRT) using intensity-modulated radiotherapy (IMRT) beams for medically inoperable Stage I lung cancer. METHODS AND MATERIALS: From February 2004 to November 2006, a total of 26 patients with 28 lesions received SBRT using a Novalis/BrainLAB system. Immobilization involved a Bodyfix vacuum cushion. A weighted abdominal belt limited respiratory excursion. Computed tomographic simulation images were acquired at rest, full inhalation, and full exhalation and were merged to generate an internal gross tumor volume (ITV). Dose was prescribed to cover the planning target volume (PTV), defined as PTV = ITV + 3-5 mm set-up margin. Heterogeneity corrections were used. Delivery of 50 Gy in five sequential fractions typically used seven nonopposing, noncoplanar beams. Image-guided target verification was provided by BrainLAB-ExacTrac. RESULTS: Among the 26 patients, the mean age was 74 years (range, 49-88 years). Of the patients, 50% were male and 50% female. The median Karnofsky performance status was 70 (range, 40-100). The median follow-up was 30.9 months (range, 10.4-51.4 months). Tissue diagnosis was contraindicated in seven patients (26.9%). There were 22 T1 (78.6%) and six T2 (21.4%) tumors. The median conformality index was 1.38 (range, 1.12-1.8). The median heterogeneity index was 1.08 (range, 1.04-1.2). One patient (3.6%) developed acute Grade 3 dyspnea and one patient developed late Grade 2 chest wall pain. Actuarial local control and overall survival at 3 years were 94.4% and 52%, respectively. CONCLUSIONS: Use of IMRT-based delivery of SBRT using restriction of tumor motion in medically inoperable lung cancer demonstrates excellent local control and favorable survival.